Please use this identifier to cite or link to this item: https://hdl.handle.net/20.500.12394/8492
Title: Defect detection on andean potatoes using deep learning and adaptive learning
Authors: Cruz Casaño, Celso De La
Cataño Sánchez, Miguel
Rojas Chavez, Freddy
Vicente Ramos, Wagner
Keywords: Papas nativas
Calidad del producto
Publisher: Universidad Continental
Issue Date: 2020
metadata.dc.date.available: 25-Feb-2021
Citation: Cruz, C., Cataño, M., Rojas, F., Vicente. (2020). Defect detection on andean potatoes using deep learning and adaptive learning. Proceedings Of The 2020 Ieee Engineering International Research Conference, Eircon 2020, 1(1). https://doi. 10.1109/EIRCON51178.2020.9254023
metadata.dc.identifier.doi: https://doi. 10.1109/EIRCON51178.2020.9254023
Abstract: Potato is economically important in Peru, which is the first potato producer in Latin America, however, the quality of native potatoes need to be improved to increment their consumption. An automatic classification process to detect potato defects is important within the entire production chain to guarantee the high quality of the product. In the present research, a Convolutional Neural Network is used to detect defects in the Huayro potato surface. This is an Andean potato originally from Peru and is special because it has very marked eyes that can complicate the differentiation from pests that leaves holes in the potato. An adaptive learning was proposed in the work, where the principal idea is to evaluate continuously the learning of the neural network to adapt the training process (in this case the training data) to increment the learning performance. The detection results were around 88.2% of F1 score, providing a good performance of the algorithm.
metadata.dc.description.note: Para acceder al artículo de su interés, puede solicitarlo a bibliotecariovirtual@continental.edu.pe. Por favor, comunicarse con su correo institucional
metadata.dc.rights.accessRights: Restringido
Appears in Collections:Artículos de conferencias

Files in This Item:
There are no files associated with this item.


This item is licensed under a Creative Commons License Creative Commons